R中散点图上两点之间的显著性标签
我的数据：R中散点图上两点之间的显著性标签,r,ggplot2,plot,dplyr,R,Ggplot2,Plot,Dplyr,我的数据： structure(list(Point = c(1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L, 12L, 13L, 14L, 15L, 16L, 17L, 18L, 19L, 20L, 21L, 22L, 23L, 24L, 25L, 26L, 27L, 28L, 29L, 30L, 31L, 32L, 33L, 34L, 35L, 36L, 37L, 38L, 39L, 40L, 41L, 42L, 43L, 44L, 45L,
structure(list(Point = c(1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L,
10L, 11L, 12L, 13L, 14L, 15L, 16L, 17L, 18L, 19L, 20L, 21L, 22L,
23L, 24L, 25L, 26L, 27L, 28L, 29L, 30L, 31L, 32L, 33L, 34L, 35L,
36L, 37L, 38L, 39L, 40L, 41L, 42L, 43L, 44L, 45L, 46L, 47L, 48L,
49L, 50L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L, 12L,
13L, 14L, 15L, 16L, 17L, 18L, 19L, 20L, 21L, 22L, 23L, 24L, 25L,
26L, 27L, 28L, 29L, 30L, 31L, 32L, 33L, 34L, 35L, 36L, 37L, 38L,
39L, 40L, 41L, 42L, 43L, 44L, 45L, 46L, 47L, 48L, 49L, 50L),
DF_FA_L = c(0.723876631, 0.736984528, 0.715005484, 0.689702567,
0.652340718, 0.602542524, 0.558524996, 0.515559258, 0.476045448,
0.440791984, 0.435388397, 0.433995996, 0.450236063, 0.461067635,
0.450821663, 0.406453595, 0.36881377, 0.368414258, 0.399242306,
0.434842762, 0.448778794, 0.450645853, 0.473092464, 0.502696464,
0.507365944, 0.498556214, 0.482145956, 0.458311758, 0.423308377,
0.385789401, 0.362710119, 0.351632877, 0.336368766, 0.327589544,
0.322429925, 0.319228948, 0.324069718, 0.335910091, 0.344128766,
0.361908972, 0.377642905, 0.382828373, 0.38802394, 0.385629004,
0.376905508, 0.365854595, 0.354565575, 0.346827766, 0.340045925,
0.344910972, 0.714518667, 0.728961368, 0.701283807, 0.663229965,
0.613014667, 0.547104, 0.504106246, 0.487034053, 0.451825246,
0.442370175, 0.438668316, 0.450059526, 0.478947649, 0.481134439,
0.446763544, 0.396206754, 0.357049368, 0.343943632, 0.376060404,
0.413613877, 0.434964895, 0.451208632, 0.470569193, 0.515300737,
0.543379719, 0.550050702, 0.541725807, 0.517293316, 0.485205246,
0.438844404, 0.395223491, 0.374209193, 0.354036316, 0.340668123,
0.326388667, 0.328114842, 0.342721667, 0.357620474, 0.372856842,
0.377362316, 0.393890737, 0.419330684, 0.419797667, 0.423127684,
0.421407509, 0.403711632, 0.39075314, 0.373226596, 0.348689877,
0.329466947), DF_FA_R = c(0.279912032, 0.306765439, 0.327785755,
0.355029826, 0.393800091, 0.44807915, 0.500145704, 0.52518085,
0.513479676, 0.498788964, 0.471167874, 0.444077727, 0.405423269,
0.374111696, 0.336296723, 0.290903704, 0.245428277, 0.207306561,
0.192131277, 0.193623134, 0.218199818, 0.242609257, 0.275690593,
0.305088802, 0.340290617, 0.380668937, 0.407181352, 0.427695356,
0.452447949, 0.449012126, 0.426914032, 0.400893245, 0.365861043,
0.345163874, 0.324515277, 0.305764024, 0.298522166, 0.298830834,
0.301616281, 0.304933115, 0.303430024, 0.307914826, 0.329325708,
0.349910727, 0.35703696, 0.352538779, 0.345419684, 0.338729395,
0.331719186, 0.334689565, 0.293618667, 0.30652786, 0.323910193,
0.334828491, 0.37942207, 0.428091754, 0.455930368, 0.478020105,
0.484362053, 0.501357439, 0.482654246, 0.490658667, 0.488896421,
0.471009596, 0.451751193, 0.443464982, 0.423077596, 0.405938053,
0.371860298, 0.342142386, 0.355380404, 0.336650965, 0.306194123,
0.307005667, 0.331578158, 0.393752421, 0.428736263, 0.434643421,
0.471135439, 0.485811825, 0.490740421, 0.464038193, 0.436188053,
0.381632737, 0.330827035, 0.302487754, 0.289443614, 0.295707035,
0.310712982, 0.320383877, 0.316538596, 0.333027772, 0.349954807,
0.368749877, 0.370285947, 0.369342158, 0.364773474, 0.368712281,
0.354579614, 0.355067965), DF_RD_L = c(0.00128287, 0.001346415,
0.001389324, 0.00139913, 0.001387198, 0.001263581, 0.001176972,
0.001140379, 0.001122925, 0.001084178, 0.001079348, 0.00108896,
0.001085937, 0.001103557, 0.001123668, 0.00108613, 0.00107296,
0.001127423, 0.001197549, 0.001237273, 0.001338632, 0.00140204,
0.001453071, 0.001519708, 0.001549107, 0.00155198, 0.00150604,
0.001412095, 0.001324316, 0.001200802, 0.001097542, 0.001016119,
0.000963012, 0.000931372, 0.000900976, 0.000881988, 0.000850344,
0.000821751, 0.000819154, 0.000832779, 0.000848632, 0.000855727,
0.000886138, 0.000928174, 0.000967573, 0.000993269, 0.00102087,
0.001044502, 0.001108162, 0.001147996, 0.001030544, 0.001002509,
0.000955719, 0.000960175, 0.000929596, 0.000859965, 0.000856088,
0.000872825, 0.000891491, 0.000911193, 0.000971596, 0.000966702,
0.000929737, 0.000848895, 0.00084314, 0.00090893, 0.000922965,
0.000901526, 0.000897684, 0.000943158, 0.001035895, 0.001122333,
0.001116579, 0.001220842, 0.001180579, 0.001107, 0.000939316,
0.000837246, 0.000755596, 0.000709491, 0.000701351, 0.00068907,
0.000685053, 0.000695982, 0.000714667, 0.000748246, 0.000763649,
0.000784035, 0.000780456, 0.000785526, 0.000883333, 0.000923246,
0.000973, 0.000999053, 0.000966965, 0.000956228, 0.000990807,
0.001019947, 0.001032, 0.001015088), DF_RD_R = c(0.001482767,
0.001472708, 0.001472478, 0.00144036, 0.001390383, 0.001321597,
0.001184138, 0.001090482, 0.001036292, 0.000992798, 0.00100483,
0.001011154, 0.001038285, 0.001050253, 0.001042162, 0.001114103,
0.001193858, 0.001285597, 0.001391779, 0.001459791, 0.001526862,
0.001556233, 0.0015487, 0.001586964, 0.001553826, 0.001558518,
0.001608079, 0.001625, 0.001649866, 0.001597375, 0.001556644,
0.001644312, 0.001805107, 0.001960146, 0.002029423, 0.002055767,
0.002054854, 0.002002909, 0.001907099, 0.001820692, 0.001730158,
0.001669328, 0.001597581, 0.001507957, 0.001395277, 0.001349368,
0.001355585, 0.001372605, 0.001353186, 0.001293146, 0.001227825,
0.001200614, 0.001173175, 0.001147842, 0.001152842, 0.001008702,
0.00098614, 0.001007509, 0.000980421, 0.000940018, 0.000966193,
0.00101586, 0.000984737, 0.000933228, 0.000892789, 0.000954667,
0.001052895, 0.001099088, 0.001107298, 0.001228842, 0.001332491,
0.001425088, 0.001486649, 0.001470333, 0.001509263, 0.001441,
0.001411895, 0.001404947, 0.001355175, 0.001309789, 0.001320947,
0.001307368, 0.001367386, 0.001385386, 0.001371596, 0.001356842,
0.001350632, 0.001298965, 0.001209105, 0.001162, 0.001164649,
0.001150386, 0.001157684, 0.001149298, 0.001122561, 0.00106893,
0.001050825, 0.001104351, 0.001050544, 0.001091544), AgeGroup = c("Old",
"Old", "Old", "Old", "Old", "Old", "Old", "Old", "Old", "Old",
"Old", "Old", "Old", "Old", "Old", "Old", "Old", "Old", "Old",
"Old", "Old", "Old", "Old", "Old", "Old", "Old", "Old", "Old",
"Old", "Old", "Old", "Old", "Old", "Old", "Old", "Old", "Old",
"Old", "Old", "Old", "Old", "Old", "Old", "Old", "Old", "Old",
"Old", "Old", "Old", "Old", "Young", "Young", "Young", "Young",
"Young", "Young", "Young", "Young", "Young", "Young", "Young",
"Young", "Young", "Young", "Young", "Young", "Young", "Young",
"Young", "Young", "Young", "Young", "Young", "Young", "Young",
"Young", "Young", "Young", "Young", "Young", "Young", "Young",
"Young", "Young", "Young", "Young", "Young", "Young", "Young",
"Young", "Young", "Young", "Young", "Young", "Young", "Young",
"Young", "Young", "Young", "Young")), class = "data.frame", row.names = c(NA,
-100L))
Myplot <- ggplot(DF, aes(x = Point, y = DF_FA_L, color = AgeGroup)) +
geom_point(aes(shape=AgeGroup))
rawDF_tTest = lapply(rawDF_tTest [c(-1,-2,-3)], function(x) t.test(x ~ AgeGroup, data = rawDF_tTest , rate = 0.1, var.equal = T))
rawDF_tTest = data.frame(do.call(rbind, rawDF_tTest ))
# color pallete
myPalette <- colorRampPalette(c("firebrick","orange","yellow1","turquoise4"))
ggplot(rawDF_tTest , aes(x = 1:50, y =log10(as.numeric(rawDF_tTest $p.value)))) +
geom_line(aes(color = as.numeric(rawDF_tTest $p.value)), size = 3) +
scale_colour_gradientn(colours = myPalette(100), limits=c(-0.01, 1))
#彩色托盘
myPalette您可以向绘图数据中添加两个其他变量：1）重要符号的y轴位置（例如星号），例如仅一个DF_FA_L+0.05，2）重要符号形状（小于alpha的为星号，大于alpha的为空）。你可以在你的图表上画出来。问题是，鉴于数据中确实存在一些时间依赖性和层次结构，t检验是否是对您来说最好的统计检验。如果你向我解释你的数据，我也许能为你指出一个更好的模型。@AdamB。这样：ggplot（DF，aes（x=Point，（y=DF\u FA\u L+0.05,2），color=AgeGroup））+geom\u Point（aes（shape=AgeGroup））
？这些数据是年轻人和老年人特定体素的MRI数据。为了简单起见，我在不同年龄组的每个主题上有50个平均体素。我根据做类似工作的出版物选择了t检验。有了这类数据，你最好使用某种混合效应模型（因为辛普森悖论——如果你看到人与人之间的某种模式，即平均而言，人与人之间可能完全不同，反之亦然）。这样，您就不必取任何平均值，您的测试将更加强大，并且能够充分控制I型错误率。我建议查看brms
软件包，它相对容易适合一些非常酷的模型：。但是如果你真的想做t检验，那么首先获取你的df并创建新变量。df%>%mutate（signif_y=df_FA_L+0.05，signif_s=ifelse（p.value<0.05，“星号”，“n”）
。之后，您可以在第一个绘图中使用代码添加显著性点。谢谢！为了时间起见，我现在将应用t-test，但也将研究混合模型。您可以在绘图数据中添加两个其他变量：1）显著性符号（例如星号）的y轴位置，例如仅DF_FA_L+0.05，2）显著性符号形状（小于alpha的为星号，大于alpha的为空）。你可以在你的图表上画出来。问题是，鉴于数据中确实存在一些时间依赖性和层次结构，t检验是否是对您来说最好的统计检验。如果你向我解释你的数据，我也许能为你指出一个更好的模型。@AdamB。这样：ggplot（DF，aes（x=Point，（y=DF\u FA\u L+0.05,2），color=AgeGroup））+geom\u Point（aes（shape=AgeGroup））
？这些数据是年轻人和老年人特定体素的MRI数据。为了简单起见，我在不同年龄组的每个主题上有50个平均体素。我根据做类似工作的出版物选择了t检验。有了这类数据，你最好使用某种混合效应模型（因为辛普森悖论——如果你看到人与人之间的某种模式，即平均而言，人与人之间可能完全不同，反之亦然）。这样，您就不必取任何平均值，您的测试将更加强大，并且能够充分控制I型错误率。我建议查看brms
软件包，它相对容易适合一些非常酷的模型：。但是如果你真的想做t检验，那么首先获取你的df并创建新变量。df%>%mutate（signif_y=df_FA_L+0.05，signif_s=ifelse（p.value<0.05，“星号”，“n”）
。之后，您可以在第一个绘图中使用代码添加显著性点。谢谢！为了时间起见，我现在将应用t-test，但也将研究混合模型。
# color pallete
myPalette <- colorRampPalette(c("firebrick","orange","yellow1","turquoise4"))
ggplot(rawDF_tTest , aes(x = 1:50, y =log10(as.numeric(rawDF_tTest $p.value)))) +
geom_line(aes(color = as.numeric(rawDF_tTest $p.value)), size = 3) +
scale_colour_gradientn(colours = myPalette(100), limits=c(-0.01, 1))